Construction of an Intelligent Decision-Making System for Pavement Maintenance of Gansu Highway Based on DeepSeek

Pavement maintenance decision-making is the key to determining the maintenance program and ensuring the maintenance effect. Still, the existing pavement maintenance decision-making methods have problems, such as incomplete and inaccurate data. Based on this, this study develops an intelligent decision-making system for pavement maintenance on highways in Gansu Province by combining DeepSeek artificial intelligence technology with dynamic capability theory. The proposed framework integrates multi-source data fusion, predictive analytics, and organizational collaboration mechanisms to address the systematic challenges of resource allocation and decentralized decision-making. A spatio-temporal graph convolutional network enables accurate pavement performance modelling, while a redesigned decision-making process enhances cross-departmental coordination through game-theoretic optimization and blockchain-based traceability. The results show significant improvements in operational efficiency, risk responsiveness, and organizational learning, validating the architecture’s ability to rack up validation at both the technical and institutional levels of infrastructure management and providing a technical reference for pavement maintenance decisions.